This repo contains PyTorch implementation for paper 3D Small Object Detection with Dynamic Spatial Pruning based on MMDetection3D.
3D Small Object Detection with Dynamic Spatial Pruning
Xiuwei Xu*, Zhihao Sun*, Ziwei Wang, Hongmin Liu, Jie Zhou, Jiwen Lu
- [2023/6/04]: We transfer DSPDet3D to extremely large scenes and show great performance! Demo will be released in our project page.
- [2023/5/01]: Code release.
Overall pipeline of DSPDet3D:
For data preparation and environment setup:
For training and evaluation:
We provide the checkpoints for quick reproduction of the results reported in the paper. The pruning threshold can be adjusted freely to tradeoff between accuracy and efficiency without any finetuning.
Benchmark | mAP@0.25 | mAP@0.5 | Downloads |
---|---|---|---|
ScanNet-md40 | 65.25 | 53.66 | model |
TO-SCENE-down | 63.67 | 55.71 | model |
Comparison with state-of-the-art methods on TO-SCENE dataset:
Visualization results on ScanNet:
Visualization results on Matterport3D:
We thank a lot for the flexible codebase of FCAF3D and valuable datasets provided by ScanNet and TO-SCENE.
If this work is helpful for your research, please consider citing the following BibTeX entry.
@article{xu2023dsp,
title={3D Small Object Detection with Dynamic Spatial Pruning},
author={Xiuwei Xu and Zhihao Sun and Ziwei Wang and Hongmin Liu and Jie Zhou and Jiwen Lu},
journal={arXiv preprint arXiv:2305.03716},
year={2023}
}